A SAS DLPy model is trained using the Functional API with two input branches: one Conv2d branch for image features and one Dense branch for tabular metadata. How are the two separate input layers declared in DLPy's Functional API?
Select an answer to reveal the explanation.
Short Explanation and Infographic
Here's the deal — b is correct because in DLPy's Functional API, multi-input models require a separate InputLayer() for each distinct input modality, each specifying the appropriate shape (e.g., height/width/channels for images, n_features for tabular). These separate input layers are then passed as starting points for their respective processing branches before merging.
Full explanation below image
Full Explanation
B is correct because in DLPy's Functional API, multi-input models require a separate InputLayer() for each distinct input modality, each specifying the appropriate shape (e.g., height/width/channels for images, n_features for tabular). These separate input layers are then passed as starting points for their respective processing branches before merging. A is wrong; a single InputLayer cannot describe two different input shapes. C is wrong; SecondaryInput() is not a DLPy class. D is wrong; the Functional API is the approach DLPy provides for multi-input architectures.